BGE-M3
BGE-M3 is BAAI’s open-weight multilingual embedding model, covering more than 100 languages. It turns inputs of up to 8,192 tokens into 1,024-dimensional vectors for semantic search, retrieval and clustering across languages.
Per 1M tokens
$0.15
Dimensions
1,024
Max input
8K
tokens per item
1M docs × 500 tokens
$75.00
to embed once
Pricing
USD per 1M input tokensInput
$0.15
1M documents
$75.00
500 tokens each, embedded once
Specs
- Model ID
text-embedding-bge-m3- Endpoint
POST /api/v1/embeddings- Dimensions
- 1,024
- Max input
- 8,192 tokens per item
- Added
- Mar 14, 2025
- Weights
- Open
POST
/api/v1/embeddingscurl https://api.venice.ai/api/v1/embeddings \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "text-embedding-bge-m3",
"input": "Private AI for everyone."
}'Privacy
Tier 1
Anonymized
Included
Tier 2 · this model
Private
Zero data retention, enforced by contract. Prompts and outputs aren’t stored.
Tier 3
TEE
Not available
Tier 4
End-to-end encrypted
Not available